Fault diagnosis of machine tools and other mechanical equipment is essentially a process of pattern recognition, i.e. the process of classifying the operational data of the equipment under fault from the normal operational data. However, traditional support vector machine based fault diagnosis is performed under the condition of sample balancing, i.e. the number of samples contained in faulty data and normal data is approximately equal, although SVM classifiers have shown good results for such data sets and have gained wide application. The aim of this paper is to investigate machine tool fault diagnosis based on support vector machines. The necessity of machine tool spindle bearing fault diagnosis is analysed, and an improved support vector machine rolling bearing fault diagnosis method based on wavelet packet decomposition is proposed. Wavelet packet decomposition is performed for feature extraction and then the extracted feature vectors are imported into three optimised bearing fault diagnosis models, Gs-Pca-Lssvm, Ga-Pca-Lssvm and Pso-Pca-Lssvm, and the experimental results show that The accuracy of all three models is 95% and above.

Yanwei Wang. Machine Tool Fault Diagnosis Based on Support Vector Machine. Machine Learning Theory and Practice (2022), Vol. 3, Issue 3: 35-42. https://doi.org/10.38007/ML.2022.030305.

[1] Alicja Jasinska-Piadlo, Raymond R. Bond, Pardis Biglarbeigi, Rob Brisk, Patricia Campbell, David J. McEneaney: What can machines learn about heart failure? A systematic literature review. Int. J. Data Sci. Anal. 13(3): 163-183 (2022) https://doi.org/10.1007/s41060-021-00300-1

[2] Sarah Jabbour, David Fouhey, Ella Kazerooni, Jenna Wiens, Michael W. Sjoding: Combining chest X-rays and electronic health record (EHR) data using machine learning to diagnose acute respiratory failure. J. Am. Medical Informatics Assoc. 29(6): 1060-1068 (2022) https://doi.org/10.1093/jamia/ocac030

[3] Bhaskar Roy, Debabrata Bera, Somya Nigam, S. K. Upadhyay: A study of turbine failure pattern: a model optimization using machine learning. Int. J. Syst. Assur. Eng. Manag. 13(4): 1761-1770 (2022) https://doi.org/10.1007/s13198-021-01542-9

[4] Muthulakshmi Muthunayagam, Kavitha Ganesan: Identification of systolic and diastolic heart failure progression with Krawtchouk moment feature-aided Harris hawks optimized support vector machine. Signal Image Video Process. 16(1): 127-135 (2022) https://doi.org/10.1007/s11760-021-01978-3

[5] Md. Mobashir Hasan Shandhi, Joanna Fan, James Alex Heller, Mozziyar Etemadi, Liviu Klein, Omer T. Inan: Estimation of Changes in Intracardiac Hemodynamics Using Wearable Seismocardiography and Machine Learning in Patients With Heart Failure: A Feasibility Study. IEEE Trans. Biomed. Eng. 69(8): 2443-2455 (2022) https://doi.org/10.1109/TBME.2022.3147066

[6] M. Z. Naser: Can past failures help identify vulnerable bridges to extreme events? A biomimetical machine learning approach. Eng. Comput. 37(2): 1099-1131 (2021) https://doi.org/10.1007/s00366-019-00874-2

[7] Naira Firdous, Sushil Bhardwaj, Amjad Husain Bhat: Prevention of autopsy by establishing a cause-effect relationship between pulmonary embolism and heart-failure using machine learning. Int. J. Comput. Appl. Technol. 66(2): 165-171 (2021) https://doi.org/10.1504/IJCAT.2021.119769

[8] Gabrielle Gauthier Melançon, Philippe Grangier, Eric Prescott-Gagnon, Emmanuel Sabourin, Louis-Martin Rousseau: A Machine Learning-Based System for Predicting Service-Level Failures in Supply Chains. INFORMS J. Appl. Anal. 51(3): 200-212 (2021) https://doi.org/10.1287/inte.2020.1055

[9] Samareh Azimpoor, Sharareh Taghipour: Optimal job scheduling and inspection of a machine with delayed failure. Int. J. Prod. Res. 58(21): 6453-6473 (2020) https://doi.org/10.1080/00207543.2019.1680900

[10] Chayma Sellami, Carlos Miranda, Ahmed Samet, Mohamed Anis Bach Tobji, François de Bertrand de Beuvron: On mining frequent chronicles for machine failure prediction. J. Intell. Manuf. 31(4): 1019-1035 (2020) https://doi.org/10.1007/s10845-019-01492-x

[11] Philippe Chrétienne: Maximizing the number of jobs scheduled at their baseline starting times in case of machine failures. J. Sched. 23(1): 135-143 (2020) https://doi.org/10.1007/s10951-019-00621-x

[12] Vepa Atamuradov, Kamal Medjaher, Fatih Camci, Noureddine Zerhouni, Pierre Dersin, Benjamin Lamoureux: Machine Health Indicator Construction Framework for Failure Diagnostics and Prognostics. J. Signal Process. Syst. 92(6): 591-609 (2020) https://doi.org/10.1007/s11265-019-01491-4

[13] Bashir Mohammed, Irfan Awan, Hassan Ugail, Muhammad Younas: Failure prediction using machine learning in a virtualised HPC system and application. Clust. Comput. 22(2): 471-485 (2019) https://doi.org/10.1007/s10586-019-02917-1

[14] Veronica Piccialli, Marco Sciandrone: Nonlinear optimization and support vector machines. Ann. Oper. Res. 314(1): 15-47 (2022) https://doi.org/10.1007/s10479-022-04655-x

[15] Parashjyoti Borah, Deepak Gupta: Affinity and transformed class probability-based fuzzy least squares support vector machines. Fuzzy Sets Syst. 443(Part): 203-235 (2022) https://doi.org/10.1016/j.fss.2022.03.009

[16] Abdullah Jafari Chashmi, Mehdi Chehel Amirani: An automatic ECG arrhythmia diagnosis system using support vector machines optimised with GOA and entropy-based feature selection procedure. Int. J. Medical Eng. Informatics 14(1): 52-62 (2022) https://doi.org/10.1504/IJMEI.2022.119309

[17] Eslam Eldeeb, Mohammad Shehab, Hirley Alves: A Learning-Based Fast Uplink Grant for Massive IoT via Support Vector Machines and Long Short-Term Memory. IEEE Internet Things J. 9(5): 3889-3898 (2022) https://doi.org/10.1109/JIOT.2021.3101978

[18] Haimonti Dutta: A Consensus Algorithm for Linear Support Vector Machines. Manag. Sci. 68(5): 3703-3725 (2022) https://doi.org/10.1287/mnsc.2021.4042

[19] Mohammad Tanveer, Aruna Tiwari, Rahul Choudhary, M. A. Ganaie: Large-scale pinball twin support vector machines. Mach. Learn. 111(10): 3525-3548 (2022) https://doi.org/10.1007/s10994-021-06061-z